mms-tts-bem / vocab.json
sanchit-gandhi's picture
Upload tokenizer
46f540b
raw
history blame
364 Bytes
{
" ": 32,
"'": 22,
"-": 30,
"a": 1,
"b": 9,
"c": 18,
"d": 20,
"e": 4,
"f": 17,
"g": 19,
"h": 16,
"i": 2,
"j": 29,
"k": 7,
"l": 5,
"m": 8,
"n": 6,
"o": 10,
"p": 15,
"r": 21,
"s": 12,
"t": 13,
"u": 3,
"w": 11,
"y": 14,
"|": 0,
"ā": 24,
"ē": 25,
"ī": 26,
"ŋ": 28,
"ō": 27,
"ū": 23,
"–": 31
}